Purpose
Needle‐based procedures for diagnosing and treating prostate cancer, such as biopsy and brachytherapy, have incorporated three‐dimensional (3D) transrectal ultrasound (TRUS) imaging to ...improve needle guidance. Using these images effectively typically requires the physician to manually segment the prostate to define the margins used for accurate registration, targeting, and other guidance techniques. However, manual prostate segmentation is a time‐consuming and difficult intraoperative process, often occurring while the patient is under sedation (biopsy) or anesthetic (brachytherapy). Minimizing procedure time with a 3D TRUS prostate segmentation method could provide physicians with a quick and accurate prostate segmentation, and allow for an efficient workflow with improved patient throughput to enable faster patient access to care. The purpose of this study was to develop a supervised deep learning‐based method to segment the prostate in 3D TRUS images from different facilities, generated using multiple acquisition methods and commercial ultrasound machine models to create a generalizable algorithm for needle‐based prostate cancer procedures.
Methods
Our proposed method for 3D segmentation involved prediction on two‐dimensional (2D) slices sampled radially around the approximate central axis of the prostate, followed by reconstruction into a 3D surface. A 2D U‐Net was modified, trained, and validated using images from 84 end‐fire and 122 side‐fire 3D TRUS images acquired during clinical biopsies and brachytherapy procedures. Modifications to the expansion section of the standard U‐Net included the addition of 50% dropouts and the use of transpose convolutions instead of standard upsampling followed by convolution to reduce overfitting and improve performance, respectively. Manual contours provided the annotations needed for the training, validation, and testing datasets, with the testing dataset consisting of 20 end‐fire and 20 side‐fire unseen 3D TRUS images. Since predicting with 2D images has the potential to lose spatial and structural information, comparisons to 3D reconstruction and optimized 3D networks including 3D V‐Net, Dense V‐Net, and High‐resolution 3D‐Net were performed following an investigation into different loss functions. An extended selection of absolute and signed error metrics were computed, including pixel map comparisons dice similarity coefficient (DSC), recall, and precision, volume percent differences (VPD), mean surface distance (MSD), and Hausdorff distance (HD), to assess 3D segmentation accuracy.
Results
Overall, our proposed reconstructed modified U‐Net performed with a median first quartile, third quartile absolute DSC, recall, precision, VPD, MSD, and HD of 94.1 92.6, 94.9%, 96.0 93.1, 98.5%, 93.2 88.8, 95.4%, 5.78 2.49, 11.50%, 0.89 0.73, 1.09 mm, and 2.89 2.37, 4.35 mm, respectively. When compared to the best‐performing optimized 3D network (i.e., 3D V‐Net with a Dice plus cross‐entropy loss function), our proposed method performed with a significant improvement across nearly all metrics. A computation time <0.7 s per prostate was observed, which is a sufficiently short segmentation time for intraoperative implementation.
Conclusions
Our proposed algorithm was able to provide a fast and accurate 3D segmentation across variable 3D TRUS prostate images, enabling a generalizable intraoperative solution for needle‐based prostate cancer procedures. This method has the potential to decrease procedure times, supporting the increasing interest in needle‐based 3D TRUS approaches.
Abstract Objectives Prostate biopsy (Bx) has for 3 decades been performed in a systematic, but blind fashion using 2D ultrasound (US). Herein is described the initial clinical evaluation of a 3D Bx ...tracking and targeting device (Artemis; Eigen, Grass Valley, CA). Our main objective was to test accuracy of the new 3D method in men undergoing first and follow-up Bx to rule out prostate cancer (CaP). Materials and methods Patients in the study were men ages 35–87 years (66.1 ± 9.9), scheduled for Bx to rule out CaP, who entered into an IRB-approved protocol. A total of 218 subjects underwent conventional trans-rectal US (TRUS); the tracking system was then attached to the US probe; the prostate was scanned and a 3D reconstruction was created. All Bx sites were visualized in 3D and tracked electronically. In 11 men, a pilot study was conducted to test ability of the device to return a Bx to an original site. In 47 men, multi-parametric 3 Tesla MRI, incorporating T2-weighted images, dynamic contrast enhancement, and diffusion-weighted imaging, was performed in advance of the TRUS, allowing the stored MRI images to be fused with real-time US during biopsy. Lesions on MRI were delineated by a radiologist, assigned a grade of CaP suspicion, and fused into TRUS for biopsy targeting. Results 3D Bx tracking was completed successfully in 180/218 patients, with a success rate approaching 95% among the last 50 men. Average time for Bx with the Artemis device was 15 minutes with an additional 5 minutes for MRI fusion and Bx targeting. In the tracking study, an ability to return to prior Bx sites ( n = 32) within 1.2 ± 1.1 mm SD was demonstrated and was independent of prostate volume or location of Bx site. In the MRI fusion study, when suspicious lesions were targeted, a 33% Bx-positivity rate was found compared with a 7% positivity rate for systematic, nontargeted Bx (19/57 cores vs. 9/124 cores, P = 0.03). Conclusion Use of 3D tracking and image fusion has the potential to transform MRI into a clinical tool to aid biopsy and improve current methods for diagnosis and follow-up of CaP.
Abstract
Breast cancer screening has substantially reduced mortality across screening populations. However, a clinical need persists for more accessible, cost-effective, and robust approaches for ...increased-risk and diverse patient populations, especially those with dense breasts where screening mammography is suboptimal. We developed and validated a cost-effective, portable, patient-dedicated three-dimensional (3D) automated breast ultrasound (ABUS) system for point-of-care breast cancer screening. The 3D ABUS system contains a wearable, rapid-prototype 3D-printed dam assembly, a compression assembly, and a computer-driven 3DUS scanner, adaptable to any commercially available US machine and transducer. Acquisition is operator-agnostic, involves a 40-second scan time, and provides multiplanar 3D visualization for whole-breast assessment. Geometric reconstruction accuracy was evaluated with a 3D grid phantom and tissue-mimicking breast phantoms, demonstrating linear measurement and volumetric reconstruction errors < 0.2 mm and < 3%, respectively. The system’s capability was demonstrated in a healthy male volunteer and two healthy female volunteers, representing diverse patient geometries and breast sizes. The system enables comfortable ultrasonic coupling and tissue stabilization, with adjustable compression to improve image quality while alleviating discomfort. Moreover, the system effectively mitigates breathing and motion, since its assembly affixes directly onto the patient. While future studies are still required to evaluate the impact on current clinical practices and workflow, the 3D ABUS system shows potential for adoption as an alternative, cost-effective, dedicated point-of-care breast cancer screening approach for increased-risk populations and limited-resource settings.
Carotid ultrasound atherosclerosis measurements, including those of the arterial wall and plaque, provide a way to monitor patients at risk of vascular events. Our objective was to examine carotid ...ultrasound plaque texture measurements and the change in carotid plaque texture during 1 year in patients at risk of events and to compare these with measurements of plaque volume and other risk factors as predictors of vascular events.
We evaluated 298 patients with carotid atherosclerosis using 3-dimensional (3D) ultrasound at baseline and after 1 year and measured carotid plaque volume and 376 measures of plaque texture. Patients were followed up to 5 years (median range, 3.12 0.77-4.66) for myocardial infarction, transient ischemic attack, and stroke. Sparse Cox regression was used to select the most predictive plaque texture measurements in independent training sets using a 10-fold cross-validation, repeated 5×, to ensure unbiased results.
Receiver operator curves and Kaplan-Meier analysis showed that changes in texture and total plaque volume combined provided the best predictor of vascular events. In multivariate Cox regression, changes in plaque texture (median hazard ratio, 1.4; P<0.001) and total plaque volume (median hazard ratio, 1.5 per 100 mm(3); P<0.001) were both significant predictors, whereas the Framingham risk score was not.
Changes in both plaque texture and volume are strongly predictive of vascular events. In high-risk patients, 3D ultrasound plaque measurements should be considered for vascular event risk prediction.
Previous studies have shown the presence of ulceration in atherosclerotic plaque either by categorizing the plaque as complex (irregular morphology with ulcers) or smooth or by quantifying the number ...of ulcers observed in a specific region of interest. The aim of this study was to quantify carotid total ulcer volume by 3-dimensional ultrasound to investigate the relationship of total ulcer volume to vascular events (strokes, transient ischemic attack, myocardial infarction, revascularization, or death because of cardiovascular reasons).
In total, 349 at-risk subjects provided written informed consent to carotid 3-dimensional ultrasound and were analyzed for ulcerations. Ulcer volume was defined as a distinct discontinuity in an atherosclerotic plaque, with a volume≥1.00 mm3 as measured using manual segmentation. The sum of the volumes of all ulcers seen in both carotids was the total ulcer volume. Participants were monitored for ≤5 years for outcomes, including cardiovascular events and death.
Kaplan-Meier survival analysis showed that subjects with total ulcer volume≥5 mm3 experienced a significantly higher risk of developing stroke, transient ischemic attack, or death (P=0.009) and of developing stroke/transient ischemic attack/death/myocardial infarction/revascularization (P=0.017). Lower ulcer volumes did not predict events nor did ulcer depth.
Volume of carotid ulceration on 3-dimensional ultrasound predicts cardiovascular events. In addition to improving risk stratification, ulceration is a potential therapeutic target.
This study evaluated the reproducibility and modality differences of prostate contouring after brachytherapy implant using three-dimensional (3D) transrectal ultrasound (3DTRUS), T2-weighted magnetic ...resonance (MR), and computed tomography (CT) imaging.
Seven blinded observers contoured 10 patients' prostates, 30 day postimplant, on 3DTRUS, MR, and CT images to assess interobserver variability. Randomized images were contoured twice by each observer. We analyzed length and volume measurements and performed a 3D analysis of intra- and intermodality variation.
Average volume ratios were 1.16 for CT/MR, 0.90 for 3DTRUS/MR, and 1.30 for CT/3DTRUS. Overall contouring variability was largest for CT and similar for MR and 3DTRUS. The greatest variability of CT contours occurred at the posterior and anterior portions of the midgland. On MR, overall variability was smaller, with a maximum in the anterior region. On 3DTRUS, high variability occurred in anterior regions of the apex and base, whereas the prostate-rectum interface had the smallest variability. The shape of the prostate on MR was rounder, with the base and apex of similar size, whereas CT contours had broad, flat bases narrowing toward the apex. The average percent of surface area that was significantly different (95% confidence interval) for CT/MR was 4.1%; 3DTRUS/MR, 10.7%; and CT/3DTRUS, 6.3%. The larger variability of CT measurements made significant differences more difficult to detect.
The contouring of prostates on CT, MR, and 3DTRUS results in systematic differences in the locations of and variability in prostate boundary definition between modalities. MR and 3DTRUS display the smallest variability and the closest correspondence.
The past two decades have witnessed developments of new imaging techniques that provide three-dimensional images about the interior of the human body in a manner never before available. Ultrasound ...(US) imaging is an important cost-effective technique used routinely in the management of a number of diseases. However, two-dimensional viewing of three-dimensional anatomy, using conventional two-dimensional US, limits our ability to quantify and visualize the anatomy and guide therapy, because multiple two-dimensional images must be integrated mentally. This practice is inefficient, and may lead to variability and incorrect diagnoses. Investigators and companies have addressed these limitations by developing three-dimensional US techniques. Thus, in this paper, we review the various techniques that are in current use in three-dimensional US imaging systems, with a particular emphasis placed on the geometric accuracy of the generation of three-dimensional images. The principles involved in three-dimensional US imaging are then illustrated with a diagnostic and an interventional application: (i) three-dimensional carotid US imaging for quantification and monitoring of carotid atherosclerosis and (ii) three-dimensional US-guided prostate biopsy.
It is currently unknown whether dietary weight loss interventions can induce regression of carotid atherosclerosis.
In a 2-year Dietary Intervention Randomized Controlled Trial-Carotid ...(DIRECT-Carotid) study, participants were randomized to low-fat, Mediterranean, or low-carbohydrate diets and were followed for changes in carotid artery intima-media thickness, measured with standard B-mode ultrasound, and carotid vessel wall volume (VWV), measured with carotid 3D ultrasound. Of 140 complete images of participants (aged 51 years; body mass index, 30 kg/m(2); 88% men), higher baseline carotid VWV was associated with increased intima-media thickness, age, male sex, baseline weight, blood pressure, and insulin levels (P<0.05 for all). After 2 years of dietary intervention, we observed a significant 5% regression in mean carotid VWV (-58.1 mm(3;) 95% confidence interval, -81.0 to -35.1 mm(3); P<0.001), with no differences in the low-fat, Mediterranean, or low-carbohydrate groups (-60.69 mm(3), -37.69 mm(3), -84.33 mm(3), respectively; P=0.28). Mean change in intima-media thickness was -1.1% (P=0.18). A reduction in the ratio of apolipoprotein B(100) to apolipoprotein A1 was observed in the low-carbohydrate compared with the low-fat group (P=0.001). Participants who exhibited carotid VWV regression (mean decrease, -128.0 mm(3); 95% confidence interval, -148.1 to -107.9 mm(3)) compared with participants who exhibited progression (mean increase, +89.6 mm(3); 95% confidence interval, +66.6 to +112.6 mm(3)) had achieved greater weight loss (-5.3 versus -3.2 kg; P=0.03), greater decreases in systolic blood pressure (-6.8 versus -1.1 mm Hg; P=0.009) and total homocysteine (-0.06 versus +1.44 mumol/L; P=0.04), and a higher increase of apolipoprotein A1 (+0.05 versus -0.00 g/L; P=0.06). In multivariate regression models, only the decrease in systolic blood pressure remained a significant independent modifiable predictor of subsequent greater regression in both carotid VWV (beta=0.23; P=0.01) and intima-media thickness (beta=0.28; P=0.008) levels.
Two-year weight loss diets can induce a significant regression of measurable carotid VWV. The effect is similar in low-fat, Mediterranean, or low-carbohydrate strategies and appears to be mediated mainly by the weight loss-induced decline in blood pressure. Clinical Trial Registration- http://www.clinicaltrials.gov. Unique Identifier: NCT00160108.
Measurement of carotid plaque volume and its progression are important tools for research and patient management. In this study, we investigate the observer variability in the measurement of plaque ...volume as determined by 3-dimensional (3D) ultrasound (US). We also investigate the effect of interslice distances (ISD) and repeated 3D US scans on measurement variability. Materials and Methods Forty 3D US patient images of plaques (range, 37.43 to 604.1 mm3) were measured by manual planimetry. We applied ANOVA to determine plaque volume measurement variability and reliability. Plaque volumes were measured with 9 ISDs to determine the effect of ISD on measurement variability. Additional plaque volumes were also measured from multiple 3D US scans to investigate repeated scan acquisition variability. Results Intraobserver and interobserver measurement reliabilities were 94% and 93.2%, respectively. Plaque volume measurement variability decreased with increasing plaque volume (range, 27.1% to 2.2%). Measurement precision was constant for ISDs between 1.0 and 3.0 mm, whereas plaque volume measurement variability increased with ISD. Repeated 3D US scan measurements were not different from single-scan measurements (P=0.867). Conclusions The coefficient of variation in the measurement of plaque volume decreased with plaque size. The volumetric change that must be observed to establish with 95% confidence that a plaque has undergone change is approximately 20% to 35% for plaques <100 mm3 and approximately 10% to 20% for plaques >100 mm3. Measurement precision was unchanged for ISDs <3.0 mm, whereas measurement variability increased with ISD. Repeated 3D US scans did not affect plaque volume measurement variability.
PDF
